Singing Style Investigation by Residual Siamese Convolutional Neural Networks

@article{Wang2018SingingSI,
  title={Singing Style Investigation by Residual Siamese Convolutional Neural Networks},
  author={C. Wang and G. Tzanetakis},
  journal={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2018},
  pages={116-120}
}
  • C. Wang, G. Tzanetakis
  • Published 2018
  • Computer Science
  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Investigating singing style is a difficult problem as individual styles are intertwined with melodies from different songs. In this paper, a methodology to investigate singing style is proposed. The proposed approach utilizes convolutional neural networks in a siamese architecture. In addition, we investigate variants of the networks to improve the audio feature extraction process. The potential of the proposed method for analyzing singing style is demonstrated using experiments on pop music… CONTINUE READING
    12 Citations

    Figures, Tables, and Topics from this paper.

    Unsupervised Singing Voice Conversion
    • 21
    • PDF
    A Model-Driven Exploration of Accent Within the Amateur Singing Voice
    • 1
    • PDF
    Accent Detection Within the Amateur Singing Voice
    • Sarah Ciresi, Vidya Rangasayee
    • 2019
    • 1
    • Highly Influenced
    • PDF
    The Impact of Audio Input Representations on Neural Network based Music Transcription
    • 3
    • PDF
    Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice
    • 3
    • PDF
    Multi-Label Sound Event Retrieval Using A Deep Learning-Based Siamese Structure With A Pairwise Presence Matrix
    Singer Identification Using Wavelet Transform

    References

    SHOWING 1-10 OF 14 REFERENCES
    Towards the characterization of singing styles in world music
    • 23
    • PDF
    Robust Singer Identification in Polyphonic Music using Melody Enhancement and Uncertainty-based Learning
    • 25
    • PDF
    Singer Identification in Popular Music Recordings Using Voice Coding Features
    • 148
    • PDF
    Singer Identification in Polyphonic Music Using Vocal Separation and Pattern Recognition Methods
    • 104
    • Highly Influential
    • PDF
    A Modeling of Singing Voice Robust to Accompaniment Sounds and Its Application to Singer Identification and Vocal-Timbre-Similarity-Based Music Information Retrieval
    • 75
    • PDF
    Pruning subsequence search with attention-based embedding
    • Colin Raffel, D. Ellis
    • Computer Science
    • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2016
    • 10
    • Highly Influential
    • PDF
    Aggregated Residual Transformations for Deep Neural Networks
    • 2,864
    • PDF
    Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
    • 4,966
    • PDF
    Adam: A Method for Stochastic Optimization
    • 52,552
    • Highly Influential
    • PDF
    Content-Based Music Information Retrieval: Current Directions and Future Challenges
    • 598
    • PDF